基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/Abilityai/abilities --skill setup-memory命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Generate an agent-specific `/update-dashboard` skill that keeps `dashboard.yaml` current for Trinity. Analyzes the agent's purpose and data sources, proposes metrics, gets user approval, then scaffolds a schedulable skill.
Modify an existing playbook based on conversation context or explicit instructions. Use when user wants to update, fix, extend, or refine a playbook they already have.
Create a new skill or playbook. Guides through requirements gathering and generates the appropriate template based on complexity.
| name | setup-memory |
| description | Initialize JSON-based memory system with structured sections |
| user-invocable | true |
| allowed-tools | Read, Write, Bash, AskUserQuestion |
Initialize a structured JSON memory system for persistent agent state.
Use AskUserQuestion:
Question 1: "What type of agent is this memory for?"
Question 2: "Should the memory track action history?"
mkdir -p memory
Write memory/memory_index.json:
{
"metadata": {
"schema_version": "1.0",
"created": "[ISO timestamp]",
"last_updated": "[ISO timestamp]",
"total_interactions": 0
},
"profile": {
"name": null,
"role": null,
"context": null
},
"preferences": {
"communication_style": null,
"tools": []
},
"memory": {
"key_facts": [],
"decisions": [],
"project_overviews": []
},
"context": {
"active_topics": [],
"recent_work": [],
"scratchpad": null
},
"entities": [],
"tasks": {
"active": [],
"completed": []
},
"custom": {}
}
Write memory/action_log.txt:
# Action Log
# Format: YYYY-MM-DD HH:MM:SS - Action description
# Newest entries at top
[ISO timestamp] - Memory system initialized
Write memory/memory_map.yaml:
# Memory System Map
# High-signal index of memory components
memory_index:
path: memory/memory_index.json
load: selective # Use jq queries, not full load
sections:
- profile
- preferences
- context
- entities
action_log:
path: memory/action_log.txt
load_lines: 50 # Most recent entries
custom_files: []
Add memory configuration:
## Memory System
JSON-based persistent memory in `memory/` folder.
### Loading Memory
Use `/load-memory` to load context at session start.
Load selectively - don't read entire memory_index.json.
### Updating Memory
Use `/memory-jq` for efficient field updates.
Use `/update-memory` after significant changes.
### Memory Sections
- `profile` - User/agent identity
- `preferences` - Settings and styles
- `memory.key_facts` - Important facts to remember
- `context` - Current work state
- `entities` - People, projects, orgs
- `tasks` - Active and completed items
### Action Log
`memory/action_log.txt` - Reverse chronological action history.
Newest entries at top. Load last 50 lines for context.
Report:
memory//load-memory to load context/update-memory to save changes